Enterprise digital workforce, agent platforms, control planes and work-management architecture.
Isolated function probes distinguish storing a check verdict from performing verification. Acceptance interfaces need to expose who generated a field, which proposition it covers and what evidence remains missing.
Pinned source-function probes show how approval changes action disposition, while leaving caller identity, authority scope and policy coverage as separate evidentiary questions.
Across 25 released configurations, partial score and complete acceptance reverse 34 pairwise orderings robustly to rounding. Domain weighting reverses six more, only three beyond rounding uncertainty. State the success objective before interpreting the ranking.
Two-dimensional counterexamples using explicitly chosen formulas show that irrelevant added capability or relaxed requirements can lower similarity while satisfaction scores stay unchanged. Internal demonstrations also separate score stability, choice stability and feasibility; they neither reproduce the original study nor establish real-task benefits.
Synthetic enumeration retains two incomparable minimal grants; approval needs the actual footprint and an explicit selection objective.
Pinned evaluation modules allow full goal progress with failed acceptance, and a legal plan with a safety violation. Synthetic inputs expose predicate scope, not full-system performance.
A fixed-marginal internal model counterexample shows why procurement concurrency depends on branch dependence and excess-acceptance costs, rather than information-processing speedup.
A cost sensitivity calculation on reported synthetic-document review rates shows how resource charges change choices and how rounding limits architecture rankings.
Source-derived isolated database probes admitted one consumer per race. Intentionally omitting the subsequent effect left retry refused, separating consumption evidence from external delivery and crash recovery.
Isolated probes share one consumed-approval state across success, pre-effect failure and post-effect exception. Replay control and delivery evidence require separate accounts.